Tight bounds for minimum -norm interpolation of noisy data G Wang, K Donhauser, F Yang
International Conference on Artificial Intelligence and Statistics, 10572-10602, 2022
27 2022 Fast rates for noisy interpolation require rethinking the effects of inductive bias K Donhauser, N Ruggeri, S Stojanovic, F Yang
Proceedings of the 39th International Conference on Machine Learning 162 …, 2022
22 2022 Efficient smoothing of dilated convolutions for image segmentation T Ziegler, M Fritsche, L Kuhn, K Donhauser
arXiv preprint arXiv:1903.07992, 2019
22 2019 How rotational invariance of common kernels prevents generalization in high dimensions K Donhauser, M Wu, F Yang
Proceedings of the 38th International Conference on Machine Learning 139 …, 2021
21 2021 Interpolation can hurt robust generalization even when there is no noise K Donhauser, A Tifrea, M Aerni, R Heckel, F Yang
Advances in Neural Information Processing Systems 34, 23465-23477, 2021
11 2021 Certified private data release for sparse Lipschitz functions K Donhauser, J Lokna, A Sanyal, M Boedihardjo, R Hönig, F Yang
arXiv preprint arXiv:2302.09680, 2023
5 * 2023 Strong inductive biases provably prevent harmless interpolation M Aerni, M Milanta, K Donhauser, F Yang
International Conference on Learning Representations, 2023
4 2023 Hidden yet quantifiable: A lower bound for confounding strength using randomized trials P De Bartolomeis, JA Martinez, K Donhauser, F Yang
International Conference on Artificial Intelligence and Statistics, 1045-1053, 2024
2 2024 Tight bounds for maximum -margin classifiers S Stojanovic, K Donhauser, F Yang
International Conference on Algorithmic Learning Theory, 1055-1112, 2024
1 2024 Privacy-preserving data release leveraging optimal transport and particle gradient descent K Donhauser, J Abad, N Hulkund, F Yang
arXiv preprint arXiv:2401.17823, 2024
1 2024 Detecting critical treatment effect bias in small subgroups P De Bartolomeis, J Abad, K Donhauser, F Yang
arXiv preprint arXiv:2404.18905, 2024
2024